Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
招采文件萝卜坑识别专家（招标人版）Bid Carrot Pit Tenderer 1.0.0
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent Chinese procurement compliance self-check skill with disclosed document-scanning behavior and no evidence of hidden execution, exfiltration, persistence, or destructive actions.
Before installing, treat this as a China-focused procurement compliance assistant: provide only tender materials you are allowed to share with the agent and any connected knowledge bases, verify all legal references against current official sources, and do not rely on it as a substitute for counsel on high-risk procurement decisions.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The description and operational instructions are entirely in Chinese and implicitly require Chinese-language interaction, but the file does not state that this locale is optional or limited to a justified region-specific deployment. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicitly documented and justified.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger phrases are broad enough to match ordinary requests about reviewing bidding documents, which can cause the skill to activate in contexts the user did not intend. Unintended activation can expose uploaded procurement documents to a highly specialized workflow, increasing the chance of over-collection, misclassification, or inappropriate legal/compliance guidance being applied.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
For manifest files, vague or underspecified invocation conditions can cause unintended activation. The description says the skill is '解耦可单独触发' but provides no explicit trigger phrases, scope limits, or negative examples to clarify when it should or should not activate.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
This markdown skill file presents all operational guidance and examples exclusively in Chinese. Because the file does not indicate that the skill is region-specific or provide the user a language/locale choice, it may violate language/locale policy by effectively forcing a single language.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The file is a markdown template whose title and all prescribed output content are written exclusively in Chinese, indicating the skill is expected to generate results in a fixed language. The policy only permits this when the skill offers language choice or clearly documents a justified locale restriction, which this template does not do.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
Natural-language policy violations include forcing a specific language or locale without user choice. The manifest name, description, and changelog are all Chinese-language, and there is no indication that users can select another language or that the skill is intentionally limited to Chinese-speaking users.
- Content
Static analysis
No suspicious patterns detected.